feat: multimodal image clients, workspaces, Tushare skill, test fixes

- Replace monolithic image_message_client with HTTP/OCR/legacy modules; tighten OpenAI transport + tool schemas for multimodal downgrade to OCR specialist path.
- Add image/stock workspace prompts (META/SOUL/ROLE_SYSTEM); register experts; tweak specialist agent/direct loop/query_image_attachment.
- Add bundled runtime/skills/tushare-finance (references, api_client, SKILL metadata).
- Document OCR-related env vars; admin chat tweaks; README; weixin_install Ensure-OfficialPluginRuntimeDeps helper.
- Tests: multimodal downgrade + OCR coverage, strict tool pairing in attachment replay guard, workspace contract skips _internal/_system dirs, router/trace/prompt guards.

Co-authored-by: Cursor <cursoragent@cursor.com>

runtime/types.py

@@ -42,11 +42,16 @@ def normalize_interaction_mode(raw: Any) -> InteractionMode:
 
 def normalize_requested_specialist(raw: Any) -> SpecialistId:
     specialist = str(raw or "").strip().lower()
-    if specialist == "ops":
-        return "ops"
-    if specialist == "memory":
-        return "memory"
-    return "generalist"
+    # Accept dynamic specialists discovered from workspaces (e.g. "stock").
+    # Fallback to "generalist" when unknown.
+    try:
+        from oclaw.runtime.agents.specialists import normalize_specialist_id
+
+        return normalize_specialist_id(specialist)
+    except Exception:
+        if specialist in {"ops", "memory", "generalist", "image"}:
+            return specialist
+        return "generalist"
 
 
 @dataclass(frozen=True)